Hi!
It didn't become clear to me why you divide the loss + regularization by 2*x_train.size
Is this just an arbitrary value?
cost = tf.div(tf.add(tf.reduce_sum(tf.square(Yy_model)),
tf.mul(reg_lambda, tf.reduce_sum(tf.square(w)))),
2*x_train.size)
Thank you very much.
